One of the most difficult and unsolved issues in network is the security issue, because ofcontinuous evolving nature of both threats and the measures used to detect and avoid threats. Amongdifferent types of attacks, one of the most vulnerable attacks in network security are bots that consumethe resources maliciously and exhaust them. Malicious Cloud Bandwidth Consumption (MCBC) attack isa new type of attack, where the aim of the attacker is to consume the bandwidth maliciously, in turncausing the financial burden to the cloud service host. MCBC is generally vulnerable to the internetbased web services in public cloud. MCBC mainly aims at frequently consuming the bandwidth in a slowmanner, hence affecting the pay-as-you-go utility model, causing the consumer in the form of monetaryloss. Unlike DDOS attack which is short lived and makes the resource unavailable to the user, MCBCattack is a long term attack which slowly attacks the target for an extended period and remainsundetectable. As this attack does not affect the availability issue immediately, it is not discussed much asDDOS attack. This paper discuss about how machine learning technique can be used to detect the MCBCattack in the form of request per second, any traffic violating this range are classified as MCBC attack.The proposed system consists of using semi supervised machine learning which uses labeled networktraffic for building model and unlabeled traffic to classify using the built model.
展开▼
